Summary of Pedestrian Traffic Statistics Research

As an important research direction in the field of computer vision and intelligent security, pedestrian traffic statistics have received more and more attention from the industry. This paper reviews the research on the important aspects of pedestrian flow statistics technology: feature extraction, target detection and pedestrian counting. Firstly, the typical methods of feature extraction are classified and compared according to the characteristics, and then the research on target detection and recognition is carried out. After summarizing, the pedestrian target count is introduced from the traditional method and the deep learning method respectively, and finally the future development is expected.